Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4616 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.6839. Min Act: -0.1700
Data Index: 4499206 (Open Web Text)
Max Activating Token Index: 565
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.4964. Min Act: -0.1700
Data Index: 4879032 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.4651. Min Act: -0.1700
Data Index: 7419319 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.4651. Min Act: -0.1700
Data Index: 7237537 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.4339. Min Act: -0.1700
Data Index: 697782 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.3089. Min Act: -0.1700
Data Index: 2498239 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.2776. Min Act: -0.1700
Data Index: 6870596 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.2464. Min Act: -0.1700
Data Index: 6778448 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.2464. Min Act: -0.1700
Data Index: 1947959 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.2151. Min Act: -0.1700
Data Index: 8680256 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.2151. Min Act: -0.1700
Data Index: 520673 (Open Web Text)
Max Activating Token Index: 545
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.1839. Min Act: -0.1700
Data Index: 1688113 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.1839. Min Act: -0.1700
Data Index: 6768987 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.1214. Min Act: -0.1700
Data Index: 8142858 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.1214. Min Act: -0.1700
Data Index: 513578 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.1214. Min Act: -0.1700
Data Index: 6049400 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.0901. Min Act: -0.1700
Data Index: 7574125 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.0589. Min Act: -0.1700
Data Index: 7432048 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.0589. Min Act: -0.1700
Data Index: 7790 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6839. Min Range: -6.6839
Max Act: 6.0589. Min Act: -0.1700
Data Index: 4904961 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #19